{"id":"W2533861448","doi":"10.1145/2983323.2983776","title":"Scalability of Continuous Active Learning for Reliable High-Recall Text Classification","year":2016,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Scalability; Classifier (UML); Limiting; Computer science; Recall; Artificial intelligence; Machine learning; Binary logarithm; Precision and recall; Class (philosophy); Information retrieval; Mathematics; Discrete mathematics; Database","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004428555,0.00008363697,0.0001613076,0.00004534252,0.00008400209,0.00002787218,0.0003455994,0.00005377305,0.00005027177],"category_scores_gemma":[0.0004040849,0.00005228663,0.00005757308,0.0001389468,0.00004985946,0.0002363538,0.00007636541,0.00008652566,0.00003426589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003310929,"about_ca_system_score_gemma":0.00003745252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001156269,"about_ca_topic_score_gemma":0.000003304365,"domain_scores_codex":[0.9990745,0.00007147706,0.0002030963,0.0003259589,0.0001409682,0.0001839646],"domain_scores_gemma":[0.9988586,0.0004257918,0.0001450857,0.0003266491,0.0001932219,0.00005067678],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002808352,0.00008928977,0.00615278,0.0000201889,0.000014016,1.975525e-7,0.0001613067,0.0001054482,0.01479779,0.06874889,0.0008304944,0.9090515],"study_design_scores_gemma":[0.004102294,0.001691565,0.2498337,0.0001819974,0.00002818947,0.000007244379,0.0002011434,0.5238334,0.09612308,0.03024779,0.0929279,0.0008217442],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06792028,0.000007363719,0.9254837,0.002712133,0.0002031506,0.0001709432,0.000001336314,0.0001693362,0.003331784],"genre_scores_gemma":[0.925589,0.00000361721,0.06386219,0.00003373631,0.00004512757,0.00002174977,0.000001619143,0.000006174224,0.01043684],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9082298,"threshold_uncertainty_score":0.2132187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0129889152481545,"score_gpt":0.2532292927712201,"score_spread":0.2402403775230657,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}